I understand, I think.
dvwjr, you’re saying that from a scientific perspective, dissimilar polls can’t be combined to reduce the MoE. And comebacknewt points out that because most polls over time are reporting very similar results, the results are probably true, just statistically ummeasurable.
So the real uncertainty of the results is smaller than the MoE, we just can’t measure it precisely? Wouldn’t that mean that the claim that “polls show the race in a dead heat” is only technically correct but misleading?
The problem with the 'dead-heat' within the MoE statements always made is that the individual making the statement always assumes that if the poll numbers seperating two candidates are between (1*MoE) and (2*MoE) that there is an equal probability that their is a statistical 'tie'. The problem with that statement is that there is a MoE 'centered around each reported poll number represented by a 'bell-curve' distribution.
If you were to graph the two intersecting MoEs of say Candidate A who leads Candidate B by the MoE of the poll, then you would find that the probability of a 'tie' would be the area under the intersecting curves, which means that while it is possible that lagging Candidate B is tied with leading Candidate A, it is MORE probable that Candidate A is actually ahead...
Hope this helps,
dvwjr
There are areas of error than the ones you are discussing. For example how about all those who only have a cellphone number. FCC rules say they can not be dialed by pollsters cause they have to pay for incoming calls.
And the new internet phones from companies like vonage and others can have area codes that don't always represent where the party actually lives.